• Interactive Poisson Blending on GPU
    Interactive Poisson Blending on GPU
  • 404 Not Found In Two Triangles
    404 Not Found In Two Triangles
  • Simplest and Fastest GLSL Edge Detection using Fwidth
    Simplest and Fastest GLSL Edge Detection using Fwidth

Category: Talk

Wearable Interactions Using Touch without a Touchscreen

Prof. Xing-Dong Yang presented his splendid work on “Wearable Interactions Using Touch without a Touchscreen” today at HCIL, University of Maryland, College Park. His pioneering work on MagicFinger (UIST 2012) inspired our work on HandSight. His recent work on Jetto (CHI 2018) extended the design space of micro-finger gestures; Pyro (UIST 2018) extended the haptic potential on smartwatches & smartphones; WrisText extended…


[Talk Summary] HandSight: A Touch-Based Wearable System to Increase Information Accessibility for People with Visual Impairments

My prior collaborator, Lee Stearns, presented his dissertation talk today. HandSight: A Touch-Based Wearable System to Increase Information Accessibility for People with Visual Impairments Please refer to http://www.leestearns.com for more details. An incomplete outline is summarized below: Related Work OrCam, Access Lens, Access Lens, OmniTouch, VizLens (UIST 2016), ForeSee, Google Glass, eSight, NuEyes, IrisVisio Reading / Exploring…


[Talk Summary] A large-scale analysis of YouTube videos depicting everyday thermal camera use

Matt present his Ph.D. defense today. The talk is entitled “A large-scale analysis of YouTube videos depicting everyday thermal camera use”. Both talk and slides are structured of the top quality. Please refer to http://www.cs.umd.edu/~mattm/#pubs for more details about Matt’s slides and papers. Next is a brief outline.   Energy audits and thermometric surveying are time…


[Summary] StackGAN: Text to Photo-realistic Image Synthesis

StackGAN Results

StackGAN has got nearly 200 citations since first appeared on arXiv on December 10, 2016.  The StackGAN is the first to generate 256*256 image with photo-realistic details from text description.   Generative Adversarial Network (GAN), originally proposed by Ian. It takes advantage of a generator network and a discriminator. The generator is trained to fool…